© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29216
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "council" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.14
    0.8%
    253
    +0.12
    0.7%
    500
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.03
    494
    +0.12
    0.02
    79
    +0.11
    0.02
    Negative Logits
    Ķ
    -2.64
    »¿
    -2.62
    ľ
    -2.44
    ĥ½
    -2.29
    ¿½
    -2.28
    ĵ
    -2.16
    ĨĴ
    -2.05
    ij
    -2.04
    ĥ
    -2.02
    ¹
    -1.96
    POSITIVE LOGITS
    ship
    1.80
    thouse
    1.71
    selling
    1.69
    ermost
    1.65
    rus
    1.61
    sell
    1.60
    stown
    1.56
    parse
    1.55
    :`
    1.54
    {};
    1.52
    Activations Density 3.110%

    No Known Activations